Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    programming code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     succinct
    0.47
     করবার
    0.47
     كافة
    0.46
     poseen
    0.46
     innumerable
    0.45
    ൫
    0.44
     fragmentary
    0.44
     incidences
    0.43
    tfrac
    0.42
    ্ের
    0.42
    POSITIVE LOGITS
     😊
    0.48
     😄
    0.43
    👍
    0.42
     골
    0.41
    😊
    0.41
    ama
    0.39
    📊
    0.39
     hai
    0.39
    🎉
    0.38
    ⁤
    0.38
    Act Density 0.560%

    No Known Activations